Time series model based personal verification using ear biometrics

In this paper personal verification is attempted on the basis of time series modelling using ear as a biometric. For this purpose, time series is obtained from the ear contour that gives structural information of the ear. Coordinates of the ear contour serve as time series to which namely time series AR model is applied. Recognition Rate (RR) up to 99% has been obtained. Results have been compared with existing techniques. The results demonstrate the effectiveness of technique for human verification.